Welcome! I'm Jakub Peleška

at FEE CTU in Prague

I am pioneering the field of Relational Deep Learning at the Intelligent Data Analaysis lab at FEE CTU. My PhD study focuses on the deep learning methods applied to relational databases, including graph neural architectures.

Follow me online or get in touch on jakub.peleska at cvut.cz

Research Areas

Relational Deep Learning

Extends traditional deep learning methods to be used on relational databases and similar data structures.

Graph Neural Networks

Specialized neural networks designed to operate on graph-structured data.

Responsible AI

Refers to the development and deployment of artificial intelligence systems that are ethical, fair, transparent, and accountable.

Recent Publications

XAI Desiderata for Trustworthy AI: Insights from the AI Act

TRUST AI 2025 • 2025

Task-Agnostic Contrastive Pretraining for Relational Deep Learning

MLG 2025 • 2025

REDELEX: A Framework for Relational Deep Learning Exploration

ECML PKDD 2025 • 2025

Assessing Explainability Methods for AI Safety Governance

International Conference on Large-Scale AI Risks • 2025

Tabular Transformers Meet Relational Databases

ACM Trans. Intell. Syst. Technol. • 2025